Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 412 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 3.5740. Min Range: -3.5740

Max Act: 3.5740. Min Act: -0.0000

Data Index: 1675924 (The Pile)

Max Activating Token Index: 364

Text #1

Max Range: 3.5740. Min Range: -3.5740

Max Act: 3.4038. Min Act: -0.0000

Data Index: 1131379 (The Pile)

Max Activating Token Index: 430

Text #2

Max Range: 3.5740. Min Range: -3.5740

Max Act: 3.2141. Min Act: -0.0000

Data Index: 943015 (The Pile)

Max Activating Token Index: 421

Text #3

Max Range: 3.5740. Min Range: -3.5740

Max Act: 3.2105. Min Act: -0.0000

Data Index: 740459 (The Pile)

Max Activating Token Index: 109

Text #4

Max Range: 3.5740. Min Range: -3.5740

Max Act: 3.2045. Min Act: -0.0000

Data Index: 799086 (The Pile)

Max Activating Token Index: 477

Text #5

Max Range: 3.5740. Min Range: -3.5740

Max Act: 3.1908. Min Act: -0.0000

Data Index: 903232 (The Pile)

Max Activating Token Index: 929

Text #6

Max Range: 3.5740. Min Range: -3.5740

Max Act: 3.2195. Min Act: -0.0000

Data Index: 537728 (The Pile)

Max Activating Token Index: 540

Text #7

Max Range: 3.5740. Min Range: -3.5740

Max Act: 3.1883. Min Act: -0.0000

Data Index: 961243 (The Pile)

Max Activating Token Index: 232

Text #8

Max Range: 3.5740. Min Range: -3.5740

Max Act: 3.3413. Min Act: -0.0000

Data Index: 502615 (The Pile)

Max Activating Token Index: 336

Text #9

Max Range: 3.5740. Min Range: -3.5740

Max Act: 3.2867. Min Act: -0.0000

Data Index: 251481 (The Pile)

Max Activating Token Index: 926

Text #10

Max Range: 3.5740. Min Range: -3.5740

Max Act: 2.9750. Min Act: -0.0000

Data Index: 1434908 (The Pile)

Max Activating Token Index: 919

Text #11

Max Range: 3.5740. Min Range: -3.5740

Max Act: 2.9783. Min Act: -0.0000

Data Index: 615428 (The Pile)

Max Activating Token Index: 888

Text #12

Max Range: 3.5740. Min Range: -3.5740

Max Act: 3.0996. Min Act: -0.0000

Data Index: 323875 (The Pile)

Max Activating Token Index: 261

Text #13

Max Range: 3.5740. Min Range: -3.5740

Max Act: 3.2314. Min Act: -0.0000

Data Index: 794802 (The Pile)

Max Activating Token Index: 458

Text #14

Max Range: 3.5740. Min Range: -3.5740

Max Act: 2.9364. Min Act: -0.0000

Data Index: 1512964 (The Pile)

Max Activating Token Index: 413

Text #15

Max Range: 3.5740. Min Range: -3.5740

Max Act: 3.0335. Min Act: -0.0000

Data Index: 1333587 (The Pile)

Max Activating Token Index: 857

Text #16

Max Range: 3.5740. Min Range: -3.5740

Max Act: 3.0518. Min Act: -0.0000

Data Index: 919698 (The Pile)

Max Activating Token Index: 87

Text #17

Max Range: 3.5740. Min Range: -3.5740

Max Act: 3.2128. Min Act: -0.0000

Data Index: 959611 (The Pile)

Max Activating Token Index: 732

Text #18

Max Range: 3.5740. Min Range: -3.5740

Max Act: 3.1832. Min Act: -0.0000

Data Index: 916812 (The Pile)

Max Activating Token Index: 130

Text #19

Max Range: 3.5740. Min Range: -3.5740

Max Act: 3.0230. Min Act: -0.0000

Data Index: 1781370 (The Pile)

Max Activating Token Index: 316